Data, RAG & Self-Hosted AI tag | eYssen AI

18 Articles

Data, RAG & Self-Hosted AI ×

embedding

Krisztian Eyssen

embedding

Text turned into a row of numbers, in which closeness of meaning becomes a measurable distance.

Beginner Everyone Glossary Data, RAG & Self-Hosted AI

Sep 13, 2026

fine-tuning

Krisztian Eyssen

fine-tuning

Training a finished model further on your own examples so that it handles one narrow task better or more cheaply.

Beginner Everyone Glossary Data, RAG & Self-Hosted AI

Sep 13, 2026

RAG (retrieval-augmented generation)

Krisztian Eyssen

RAG (retrieval-augmented generation)

The setup in which the model looks up the relevant passage in your own documents before it answers, and works from that.

Beginner Everyone Glossary Data, RAG & Self-Hosted AI

Sep 13, 2026

vector database

Krisztian Eyssen

vector database

A store that holds vectors and quickly finds the ones most similar to the one you are looking for.

Beginner Everyone Glossary Data, RAG & Self-Hosted AI

Sep 13, 2026

chunking

Krisztian Eyssen

chunking

Cutting documents into retrievable pieces — a bad split is the most common cause of bad answers.

Beginner Everyone Glossary Data, RAG & Self-Hosted AI

Sep 13, 2026

Fine-Tuning: When Is It Finally Worth It?

Krisztian Eyssen

Fine-Tuning: When Is It Finally Worth It?

A fine-tuned model with 350 million parameters hit a **77.6%** success rate on a tool-calling task — while a general model with 175 billion parameters managed **26%** on the same task. Five hundred times fewer parameters, three times the result. That is the real promise of fine-tuning. And meanwhile one large provider is **retiring its fine-tuning platform**: no new users are being accepted, and existing ones have until January 2027.

Advanced Developer Explainer Data, RAG & Self-Hosted AI

Sep 13, 2026

Private AI: Keeping Data Inside Your Company

Krisztian Eyssen

Private AI: Keeping Data Inside Your Company

One large provider's zero data retention agreement lists item by item which endpoints it covers — and which it does not. On the does-not list: **file upload** and the **vector store**: **exactly the two features you would use to build RAG on that platform.** And on the other side, the assumption that "local means safe": a 293-day survey found **175,108 publicly reachable local model servers** in 130 countries.

Advanced Business owner How-To Data, RAG & Self-Hosted AI

Sep 13, 2026

Local AI Runners: Which One to Pick

Krisztian Eyssen

Local AI Runners: Which One to Pick

The most important thing to know: **Ollama, LM Studio, Jan, KoboldCpp and Docker Model Runner all use the same engine** — llama.cpp, and MLX on a Mac. They do not differ in speed but in the packaging and in the **defaults**. And the defaults are exactly where the trap is: Ollama **truncates at 4,096 tokens** out of the box, even when the model could handle 256k.

Beginner Developer Tool review Ollama Data, RAG & Self-Hosted AI

Sep 13, 2026

Quantization: How Big Models Fit on Small Machines

Krisztian Eyssen

Quantization: How Big Models Fit on Small Machines

According to a unified 2026 measurement, four-bit quantization **cuts model size by 71%** and costs on average **0.43 percentage points** of accuracy. Essentially free. Except **not for everyone**: the same four-bit quantization also produced a **59%** collapse on long input, and the degradation is **up to five times worse in languages other than English** — measured across 26 languages, Hungarian among them.

Advanced Developer Explainer Data, RAG & Self-Hosted AI

Sep 13, 2026

Hardware for Local AI: VRAM, RAM and Apple Silicon

Krisztian Eyssen

Hardware for Local AI: VRAM, RAM and Apple Silicon

The rule of thumb everyone repeats says you need about half the parameter count in memory. `[Own calculation]` The four-bit weights of an eight-billion-parameter model really do eat 4.6 gigabytes — **but the same model's 128k-token context eats 18 gigabytes**, four times the model itself. Anyone who only looks at model size has worked out a fifth of the memory they actually need. And there is one measurement that turns the whole picture around: **a chip with half the GPU cores processes a prompt 83% faster than a more expensive one** — while generating a fifth slower.

Advanced Developer How-To Data, RAG & Self-Hosted AI

Sep 13, 2026

Why Run AI on Your Own Machine?

Krisztian Eyssen

Why Run AI on Your Own Machine?

Of the four usual reasons, two hold up and two do not. `[Own calculation]` Against the cheapest API tier, a $3,500 machine breaks even at **2.6 billion tokens a year** — 133 days of continuous generation. And here is the twist that holds the whole article together: **the volume at which local running pays off is exactly the volume at which the local model is no longer good enough.** There is a fifth reason, though, that nobody states out loud, and measurably it is the strongest of the lot.

Beginner Business owner Explainer Data, RAG & Self-Hosted AI

Sep 13, 2026

Keeping the Knowledge Base Fresh

Krisztian Eyssen

Keeping the Knowledge Base Fresh

A measurement built on 96 thousand question-answer pairs and 219 thousand documents found that the mere presence of outdated content causes, according to the study, **at least a 20% drop in performance**, with some models doing worse than chance. But the most important finding is not the number: **models stay appropriately uncertain when they find nothing — and are confidently wrong when they find something stale.** An empty knowledge base is less dangerous than an old one.

Intermediate Business owner How-To Data, RAG & Self-Hosted AI

Sep 13, 2026

1
2

Follow Us

Archives

Tags

Audience

Everyone Office worker Marketer Creative Business owner Developer

Category

AI Basics Safety & Risk Regulation & Policy Infrastructure & Chips Business & Deals Prompting Models & Market Writing & Content Images & Design Video & Audio Marketing & SEO Coding & Development Work & Productivity Agents & Automation Data, RAG & Self-Hosted AI Business, Law & Security

Company

OpenAI Anthropic Google xAI (Grok) Meta Microsoft Mistral Chinese labs

Format

How-To Explainer Comparison Tool review Recipe Template Troubleshooting Case study Glossary News

Level

Beginner Intermediate Advanced

Tool

OpenRouter Perplexity HeyGen ElevenLabs Suno Obsidian MCP n8n Ollama EYAS

Others

Odoo